© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 13920
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "honor" or "honour"

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    1065
    +0.16
    0.6%
    897
    +0.15
    0.6%
    596
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1065
    +0.16
    0.03
    1490
    +0.15
    0.03
    596
    +0.13
    0.02
    Negative Logits
     habet
    -0.56
     potest
    -0.52
     caufe
    -0.48
     quæ
    -0.47
    씬
    -0.47
     smtplib
    -0.46
     projekty
    -0.46
    Controllo
    -0.45
    cifix
    -0.45
    perature
    -0.44
    POSITIVE LOGITS
     honor
    1.25
     Honor
    1.21
    Honor
    1.19
     HONOR
    1.16
     honors
    1.11
     honored
    1.09
     honour
    1.09
    honor
    1.08
     honoring
    1.04
     Honors
    1.00
    Activations Density 0.090%

    No Known Activations